ACL RD-TEC 1.0 Summarization of W01-1409
Paper Title:
BUILDING A STATISTICAL MACHINE TRANSLATION SYSTEM FROM SCRATCH: HOW MUCH BANG FOR THE BUCK CAN WE EXPECT?
BUILDING A STATISTICAL MACHINE TRANSLATION SYSTEM FROM SCRATCH: HOW MUCH BANG FOR THE BUCK CAN WE EXPECT?
Primarily assigned technology terms:
- algorithm
- bootstrapping
- classification
- classifiers
- corpus translation
- data collection
- data retrieval
- decoding
- document classification
- document retrieval
- encoding
- identification
- information processing
- internet
- machine translation
- machine translation system
- matching
- morphology
- mt system
- mt systems
- multilingual information processing
- nlp
- processing
- processing technology
- question answering
- regular expression
- regular expression matching
- resource creation
- search
- spelling
- statistical approaches
- statistical machine translation
- statistical machine translation system
- statistical mt
- statistical nlp
- statistical training
- stemmer
- tokenization
- topic identification
- training algorithm
- translation method
- translation process
- translation system
- translator
- translators
- transliteration
- transliterator
- web interface
- word translation
Other assigned terms:
- approach
- case
- classification accuracy
- community
- corpora
- corpus size
- design and implementation
- document
- english language
- english language model
- english translation
- english translations
- fact
- human translation
- ibm model
- implementation
- inflection
- knowledge
- language model
- measure
- method
- multilingual information
- names
- negation
- parallel corpora
- parallel corpus
- phrase
- precision
- priori
- probabilities
- probability
- process
- quality control
- question answering task
- retrieval task
- search space
- segments
- sentence
- sentences
- source language
- source text
- standard deviation
- statistical model
- system evaluation
- system performance
- technology
- term
- terms
- test set
- text
- text segment
- tokens
- training
- training corpus
- training data
- training set
- translation candidates
- translation model
- translation quality
- translation table
- translations
- word
- word form
- word level
- words
